© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64975
    Prev
    Next
    INDEX
    Explanations

    anodized aluminum, vibrating motor, Socket Weld, High Build Epoxy

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on detailed product‐specification language—especially material names, component parts, and technical measurements in a manufacturing or engineering context.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ativar
    -1.67
    alers
    -1.63
    llac
    -1.56
     večer
    -1.55
    盉
    -1.51
    Familien
    -1.48
     şeyi
    -1.45
    Conclusão
    -1.45
     didn
    -1.44
     zí
    -1.44
    POSITIVE LOGITS
     with
    2.92
     in
    1.55
     at
    1.52
     or
    1.44
     provided
    1.40
     државе
    1.39
     for
    1.38
     through
    1.38
     all
    1.36
    靱
    1.36
    Activations Density 0.035%

    No Known Activations